CN108170792A - Question and answer bootstrap technique, device and computer equipment based on artificial intelligence - Google Patents
Question and answer bootstrap technique, device and computer equipment based on artificial intelligence Download PDFInfo
- Publication number
- CN108170792A CN108170792A CN201711447824.3A CN201711447824A CN108170792A CN 108170792 A CN108170792 A CN 108170792A CN 201711447824 A CN201711447824 A CN 201711447824A CN 108170792 A CN108170792 A CN 108170792A
- Authority
- CN
- China
- Prior art keywords
- answer
- question
- user
- keyword
- structuring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
- G06F16/243—Natural language query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
- G06F16/2425—Iterative querying; Query formulation based on the results of a preceding query
Abstract
The application proposes a kind of question and answer bootstrap technique, device and computer equipment based on artificial intelligence, and the above-mentioned question and answer bootstrap technique based on artificial intelligence includes:Receive the first keyword input by user;It according to first keyword, is engaged in the dialogue based on structuring question and answer knowledge base and the user, obtains the second keyword that the user inputs in the dialog procedure;First keyword is combined with second keyword, obtain the user treats answer problem;The Similar Problems for treating answer problem are matched in the structuring question and answer knowledge base, and retrieval obtains the answer of the Similar Problems in the structuring question and answer knowledge base using the mode of similarity calculation;The answer of the Similar Problems is supplied to the user.The application can be realized to be excavated automatically according to keyword input by user, and obtain user treats answer problem, it is only necessary to which less artificial participation improves question and answer efficiency.
Description
Technical field
This application involves search technique field more particularly to a kind of question and answer bootstrap technique based on artificial intelligence, device and
Computer equipment.
Background technology
Current miscellaneous product emerges in an endless stream, and required customer service quantity is also more and more therewith, and for same production
The problem of product, different user, often will appear a large amount of repetition or similar, artificial customer service is required for reply one by one at present, this is pair
The significant wastage of manpower, and it is usually relatively low to answer efficiency.
In existing the relevant technologies, it is generally basede on intention and/or slot position and keyword input by user (query) is solved
Still, there is intention based on the mode being intended to and/or slot position parses query input by user and/or slot position be abstracted in analysis
More difficult, the description of slot position, which is difficult to exhaustion and intention and/or the parsing of slot position, needs more artificial participation, and what is taken time and effort lacks
Point.
Invention content
The application is intended to solve at least some of the technical problems in related technologies.
For this purpose, first purpose of the application is to propose a kind of question and answer bootstrap technique based on artificial intelligence, to realize
It is excavated automatically according to keyword input by user, obtain user treats answer problem, it is only necessary to which less artificial participation improves
Question and answer efficiency.
Second purpose of the application is to propose a kind of question and answer guide device based on artificial intelligence.
The third purpose of the application is to propose a kind of computer equipment.
The 4th purpose of the application is to propose a kind of non-transitorycomputer readable storage medium.
In order to achieve the above object, the application first aspect embodiment proposes a kind of question and answer guiding side based on artificial intelligence
Method, including:Receive the first keyword input by user;According to first keyword, based on structuring question and answer knowledge base and institute
It states user to engage in the dialogue, obtains the second keyword that the user inputs in the dialog procedure;By first keyword
It is combined with second keyword, obtain the user treats answer problem;Using the mode of similarity calculation in the structure
Change and treat the Similar Problems of answer problem, and retrieve and obtain in the structuring question and answer knowledge base described in being matched in question and answer knowledge base
Obtain the answer of the Similar Problems;The answer of the Similar Problems is supplied to the user.
In the question and answer bootstrap technique based on artificial intelligence of the embodiment of the present application, receive the first keyword input by user it
Afterwards, it according to above-mentioned first keyword, is engaged in the dialogue based on structuring question and answer knowledge base and above-mentioned user, obtains above-mentioned user upper
The second keyword inputted in dialog procedure is stated, the first keyword is combined with the second keyword, obtained above-mentioned user and wait to answer
Multiple problem is matched in above structure question and answer knowledge base using the mode of similarity calculation and above-mentioned treats the similar of answer problem
Problem, and retrieval obtains the answer of above-mentioned Similar Problems in above structure question and answer knowledge base, by answering for above-mentioned Similar Problems
Case is supplied to above-mentioned user, excavated so as to realize automatically according to keyword input by user, obtains user and waits to answer
Multiple problem, it is only necessary to which less artificial participation improves question and answer efficiency.
In order to achieve the above object, the application second aspect embodiment proposes a kind of question and answer guiding dress based on artificial intelligence
It puts, including:Receiving module, for receiving the first keyword input by user;Module is obtained, for being connect according to the receiving module
The first keyword received, is engaged in the dialogue based on structuring question and answer knowledge base and the user, obtains the user in the dialogue
The second keyword inputted in the process;Binding modules for first keyword to be combined with second keyword, obtain
The user's treats answer problem;Matching module, for using the mode of similarity calculation in the structuring question and answer knowledge base
In match the Similar Problems for treating answer problem;Module is retrieved, is obtained for being retrieved in the structuring question and answer knowledge base
Obtain the answer of the Similar Problems;Module is provided, the answer of Similar Problems for the retrieval module retrieval to be obtained provides
To the user.
In the question and answer guide device based on artificial intelligence of the embodiment of the present application, receiving module receives input by user first
After keyword, module is obtained according to above-mentioned first keyword, is engaged in the dialogue based on structuring question and answer knowledge base and above-mentioned user,
Obtain the second keyword that above-mentioned user inputs in above-mentioned dialog procedure, binding modules are by the first keyword and the second keyword
With reference to obtain above-mentioned user treats answer problem, and matching module is known using the mode of similarity calculation in above structure question and answer
Know in library and match the above-mentioned Similar Problems for treating answer problem, and retrieved in above structure question and answer knowledge base by retrieval module
The answer of above-mentioned Similar Problems is obtained, module is provided, the answer of above-mentioned Similar Problems is supplied to above-mentioned user, so as to reality
It is now excavated automatically according to keyword input by user, obtain user treats answer problem, it is only necessary to which less artificial participation is promoted
Question and answer efficiency.
In order to achieve the above object, the application third aspect embodiment proposes a kind of computer equipment, including memory, processor
And the computer program that can be run on the memory and on the processor is stored in, the processor performs the calculating
During machine program, method as described above is realized.
To achieve these goals, the application fourth aspect embodiment proposes a kind of computer-readable storage of non-transitory
Medium, is stored thereon with computer program, and the computer program realizes method as described above when being executed by processor.
The additional aspect of the application and advantage will be set forth in part in the description, and will partly become from the following description
It obtains significantly or is recognized by the practice of the application.
Description of the drawings
The application is above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Significantly and it is readily appreciated that, wherein:
Fig. 1 is the flow chart of the question and answer bootstrap technique one embodiment of the application based on artificial intelligence;
Fig. 2 is the flow chart of question and answer bootstrap technique another embodiment of the application based on artificial intelligence;
Fig. 3 is the schematic diagram that question and answer guide one embodiment in question and answer bootstrap technique of the application based on artificial intelligence;
Fig. 4 is the flow chart of question and answer bootstrap technique further embodiment of the application based on artificial intelligence;
Fig. 5 is the schematic diagram that question and answer guide another embodiment in question and answer bootstrap technique of the application based on artificial intelligence;
Fig. 6 is the flow chart of question and answer bootstrap technique further embodiment of the application based on artificial intelligence;
Fig. 7 be obtain above-mentioned user in question and answer bootstrap technique of the application based on artificial intelligence treat one reality of answer problem
Apply the schematic diagram of example;
Fig. 8 be question and answer bootstrap technique of the application based on artificial intelligence in obtain above-mentioned user treat answer problem another
The schematic diagram of embodiment;
Fig. 9 is the flow chart of question and answer bootstrap technique further embodiment of the application based on artificial intelligence;
The concept one embodiment of Figure 10 to excavate output in question and answer bootstrap technique of the application based on artificial intelligence is shown
It is intended to;
The problem of Figure 11 is excavation output in question and answer bootstrap technique of the application based on artificial intelligence one embodiment is shown
It is intended to;
Figure 12 is the structure diagram of the question and answer guide device one embodiment of the application based on artificial intelligence;
Figure 13 is the structure diagram of question and answer guide device another embodiment of the application based on artificial intelligence;
Figure 14 is the structure diagram of the application computer equipment one embodiment.
Specific embodiment
Embodiments herein is described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the application, and it is not intended that limitation to the application.
Artificial intelligence (Artificial Intelligence;Hereinafter referred to as:AI it is) research, develops to simulate, extend
One new technological sciences of theory, method, technology and application system with the intelligence of extension people.Artificial intelligence is computer section
The branch learned, it attempts to understand essence of intelligence, and produces and a kind of new can be made in a manner that human intelligence is similar
The intelligence machine of reaction, the research in the field include robot, language identification, image identification, natural language processing and expert system
System etc..
Fig. 1 is the flow chart of the question and answer bootstrap technique one embodiment of the application based on artificial intelligence, as shown in Figure 1, on
Stating the question and answer bootstrap technique based on artificial intelligence can include:
Step 101, the first keyword input by user is received.
Specifically, user can input above-mentioned first keyword in the form of text, voice or picture, the present embodiment to
The mode that family inputs the first keyword is not construed as limiting.
In the description of the embodiment of the present application, knowledge base is structuring in knowledge engineering, easy to operate, is easily utilized, Quan Mianyou
The knowledge cluster of tissue is the needs solved for a certain (or certain) field question, using certain (or several) representation of knowledge
The knowledge piece set that mode was stored, and organized, manages and used in computer storage interknit.These knowledge pieces include
Knowwhy relevant with field, factual data, the heuristic knowledge obtained by expertise are determined as related in certain field
Justice, theorem and algorithm and common sense knowledge etc..
Step 102, it according to above-mentioned first keyword, is engaged in the dialogue, obtained based on structuring question and answer knowledge base and above-mentioned user
Obtain the second keyword that above-mentioned user inputs in above-mentioned dialog procedure.
Wherein, the dialogue carried out with above-mentioned user can be that single-wheel is talked with, or more wheel dialogues, the present embodiment is to this
It does not select, the present embodiment is illustrated by taking more wheel dialogues as an example.
Step 103, above-mentioned first keyword is combined with above-mentioned second keyword, obtain above-mentioned user treats that answer is asked
Topic.
Step 104, it is matched in above structure question and answer knowledge base using the mode of similarity calculation and above-mentioned waits to reply
The Similar Problems of problem, and retrieval obtains the answer of above-mentioned Similar Problems in above structure question and answer knowledge base.
Specifically, obtain above-mentioned user treat answer problem after, the mode of similarity calculation can be used above-mentioned
The above-mentioned Similar Problems for treating answer problem are matched in structuring question and answer knowledge base, so as to achieve the purpose that meet user demand.
Such as:User's treats that answer problem can be described as after more wheel dialogues:" inter-bank is taken throughout the year to be reduced or remitted ", passes through similarity calculation
Mode, it can be found that in " inter-bank is taken throughout the year to be reduced or remitted " and above structure question and answer knowledge base " inter-bank take throughout the year whether
Deduction and exemption " are synonymous statements, then " whether inter-bank is taken throughout the year reduces or remits " is the Similar Problems for treating answer problem of above-mentioned user,
Therefore the answer of acquisition " whether inter-bank is taken throughout the year reduces or remits " can be retrieved in above structure question and answer knowledge base.
Certainly, if there are problems that in above structure question and answer knowledge base treating the problem of answer is identical with above-mentioned user,
Above-mentioned user then can be directly retrieved in above structure question and answer knowledge base treat answer problem, obtains above-mentioned user and waits to answer
The answer of multiple problem.
Step 105, the answer of above-mentioned Similar Problems is supplied to above-mentioned user.
In the above-mentioned question and answer bootstrap technique based on artificial intelligence, after receiving the first keyword input by user, according to upper
The first keyword is stated, is engaged in the dialogue based on structuring question and answer knowledge base and above-mentioned user, above-mentioned user is obtained and talked with above-mentioned
The second keyword inputted in journey is combined the first keyword with the second keyword, and obtain above-mentioned user treats answer problem, makes
The above-mentioned Similar Problems for treating answer problem are matched in above structure question and answer knowledge base with the mode of similarity calculation, and
Retrieval obtains the answer of above-mentioned Similar Problems in above structure question and answer knowledge base, and the answer of above-mentioned Similar Problems is supplied to
User is stated, is excavated so as to realize automatically according to keyword input by user, obtain user treats answer problem, it is only necessary to
Less artificial participation, improves question and answer efficiency.
Fig. 2 is the flow chart of question and answer bootstrap technique another embodiment of the application based on artificial intelligence, as shown in Fig. 2,
Step 102 can include in the application embodiment illustrated in fig. 1:
Step 201, when above-mentioned first keyword is problem, based on structuring question and answer knowledge base in above-mentioned user's offer
State the corresponding at least one concept of problem.
Step 202, the concept that above-mentioned user selects from above-mentioned at least one concept is obtained, alternatively, obtaining above-mentioned user
The concept of input.
Specifically, when above-mentioned first keyword is problem, it can actively inquire that user thinks according to structuring question and answer knowledge base
What is asked is which corresponding concept of the problem, as shown in figure 3, Fig. 3 is question and answer bootstrap technique of the application based on artificial intelligence
Middle question and answer guide the schematic diagram of one embodiment.
In Fig. 3, it is assumed that the first keyword input by user is " the single limit transferred accounts is how many ", this belongs to problem, in
It can be based on structuring question and answer knowledge base and provide where the corresponding at least one concept of the above problem " could you tell me finger to above-mentioned user
A kind of business:1. inter-bank, which leads to 2. different degree, pays 3. personal mobile phone banks ... ", user is then obtained from above-mentioned at least one concept
The concept " personal mobile phone bank " of middle selection, certainly, if not including user in above-mentioned at least one concept wants the general of inquiry
It reads, then above-mentioned user can also input the concept that oneself wants inquiry.
Fig. 4 is the flow chart of question and answer bootstrap technique further embodiment of the application based on artificial intelligence, as shown in figure 4,
Step 102 can include in the application embodiment illustrated in fig. 1:
Step 401, when above-mentioned first keyword is concept, based on structuring question and answer knowledge base in above-mentioned user's offer
State the corresponding at least one problem of concept.
Step 402, the problem of above-mentioned user selects from above-mentioned at least one problem is obtained, alternatively, obtaining above-mentioned user
The problem of input.
Specifically, when above-mentioned first keyword is concept, it can actively inquire that user thinks based on structuring question and answer knowledge base
What is asked is the which aspect problem of the concept, as shown in figure 5, Fig. 5 is in question and answer bootstrap technique of the application based on artificial intelligence
Question and answer guide the schematic diagram of another embodiment.
In Fig. 5, it is assumed that the first keyword input by user is " inter-bank is led to ", this belongs to concept, in can be based on structure
Change question and answer knowledge base to above-mentioned user provide the corresponding at least one problem of above-mentioned concept " could you tell me want to ask lead to about inter-bank it is assorted
Problem:1. the single limit transferred accounts is whether how many 2. annual fees can be reduced or remitted ... ", user is then obtained from above-mentioned at least one
The problem of being selected in problem " whether annual fee can be reduced or remitted ", certainly, if not wanting to ask including user in above-mentioned at least one problem
The problem of the problem of asking, then above-mentioned user can also input oneself desired inquiry.
Fig. 6 is the flow chart of question and answer bootstrap technique further embodiment of the application based on artificial intelligence, as shown in fig. 6,
In the application embodiment illustrated in fig. 1, step 103 can include:
Step 601, based on above structure question and answer knowledge base and the first keyword, the second keyword is understood, with
The information that above-mentioned first keyword and above-mentioned second keyword include fill and replace automatically, obtains treating for above-mentioned user
Answer problem.
Specifically, based on above structure question and answer knowledge base, question and answer guiding can be not only carried out, while can also carry out
Hereafter understand, you can with the knowledge flexibly in above structure question and answer knowledge base and the first keyword to working as the of front-wheel
Two keywords are understood, realize information filling and replacement automatically, obtain above-mentioned user treats answer problem, such as Fig. 7 and Fig. 8 institutes
Show, Fig. 7 be obtain above-mentioned user in question and answer bootstrap technique of the application based on artificial intelligence treat answer problem one embodiment
Schematic diagram, Fig. 8 be obtain above-mentioned user in question and answer bootstrap technique of the application based on artificial intelligence treat that answer problem is another
The schematic diagram of a embodiment.
In Fig. 7, user is in last round of dialogue, and for " the single limit transferred accounts is how many ", this belongs to the first keyword of input
Problem, " please to the corresponding at least one concept of the above-mentioned user offer above problem in can be based on structuring question and answer knowledge base
Ask that you refer to any business:1. inter-bank, which leads to 2. different degree, pays 3. personal mobile phone banks ... ", then obtain user from it is above-mentioned at least
The concept " personal mobile phone bank " selected in one concept, providing a user answer later, " personal mobile phone bank transfer limit is
5w members ".Talk with when front-wheel, the second keyword input by user is " inter-bank is led to ", based on above structure question and answer knowledge base
With the first keyword, the second keyword is understood, with the letter included to above-mentioned first keyword and above-mentioned second keyword
Breath carry out automatically fill and replace, can obtain user treat answer problem for inter-bank lead to the single limit transferred accounts be it is how many, in
It is that can provide a user answer " inter-bank leads to limit of transferring accounts for 2w members ".
In Fig. 8, user is in last round of dialogue, and the first keyword of input is " whether inter-bank is taken throughout the year can reduce or remit ", base
The answer " inter-bank is taken throughout the year to be reduced or remitted " of the above problem is provided in structuring question and answer knowledge base to above-mentioned user.When front-wheel pair
Words, the second keyword input by user is " that year, expense was how many ", based on above structure question and answer knowledge base and the first keyword,
Second keyword is understood, is filled automatically with the information included to above-mentioned first keyword and above-mentioned second keyword
And replacement, can obtaining the answer problem for the treatment of of user, to take throughout the year be how many for inter-bank, can then provide a user answer " inter-bank
Expense is 20 yuan throughout the year ".
Fig. 9 is the flow chart of question and answer bootstrap technique further embodiment of the application based on artificial intelligence, as shown in figure 9,
Before the application embodiment illustrated in fig. 1 step 102, it can also include:
Step 901, the problems in question and answer knowledge base for treating structuring and answer are segmented by sentence.
Step 902, the word obtained by co-occurrence statistics method to participle counts, and obtains statistical information, above-mentioned system
Current term and other words can be included close to the number, current term and other words of co-occurrence not close to co-occurrence by counting information
The total degree that number and each word occur.
Step 903, the tight ness rating between the word obtained according to above-mentioned statistical information to above-mentioned participle calculates.
It specifically, can be using tight ness rating method, between the word obtained according to above-mentioned statistical information to above-mentioned participle
Tight ness rating is calculated.
Step 904, tight ness rating is more than predetermined threshold and adjacent word is combined, obtain close segment.
Wherein, above-mentioned predetermined threshold can voluntarily be set in specific implementation according to system performance and/or realization demand etc.
Fixed, the present embodiment is not construed as limiting the size of above-mentioned predetermined threshold.
Step 905, the problems in above-mentioned question and answer knowledge base for treating structuring and answer are analyzed, acquisition is above-mentioned to be waited to tie
The rule that the problems in question and answer knowledge base of structure and answer are contained, by above-mentioned rule to above-mentioned close segment at
Reason obtains initial candidate concept and initial problem set.
Step 906, it by query segment identification technology, filters out in above-mentioned initial candidate concept and is identified as query segment
Concept obtains final concept set.As shown in Figure 10, Figure 10 is excavates in question and answer bootstrap technique of the application based on artificial intelligence
The schematic diagram of concept one embodiment of output.
Step 907, it according to the problems in above-mentioned question and answer knowledge base for treating structuring and final concept set, is taken out by relationship
Take and above-mentioned initial problem set handled, obtain in the problem of above-mentioned question and answer knowledge base for treating structuring includes with it is above-mentioned most
The problem of concept tight association in whole concept set, final problem set is formed, to obtain above structure question and answer knowledge base.
Referring to Figure 11, Figure 11 is one reality the problem of output is excavated in question and answer bootstrap technique of the application based on artificial intelligence
Apply the schematic diagram of example.
In the present embodiment, step 901~step 907 can parallel be performed with step 101, can also be with step 101 successively
It performs, the present embodiment is not construed as limiting step 901~step 907 and the execution sequence of step 101.
The present embodiment can be realized is processed as structuring question and answer knowledge base by question and answer knowledge base, and people is carried out to data to reduce
The cost that work is abstracted.
Figure 12 is the structure diagram of the question and answer guide device one embodiment of the application based on artificial intelligence, and the application is real
Applying the question and answer guide device based on artificial intelligence in example can be used as a part for search engine or search engine to realize this Shen
Please embodiment provide the question and answer bootstrap technique based on artificial intelligence.As shown in figure 12, the above-mentioned question and answer based on artificial intelligence are drawn
Leading device can include:Receiving module 1201 obtains module 1202, binding modules 1203, matching module 1204, retrieval module
1205 and provide module 1206;
Wherein, receiving module 1201, for receiving the first keyword input by user;Specifically, user can with text,
The form of voice or picture inputs above-mentioned first keyword, and the mode that the present embodiment inputs user the first keyword does not limit
It is fixed.
Module 1202 is obtained, for the first keyword received according to receiving module 1201, based on structuring question and answer knowledge
Library engages in the dialogue with above-mentioned user, obtains the second keyword that above-mentioned user inputs in above-mentioned dialog procedure;
In the description of the embodiment of the present application, knowledge base is structuring in knowledge engineering, easy to operate, is easily utilized, Quan Mianyou
The knowledge cluster of tissue is the needs solved for a certain (or certain) field question, using certain (or several) representation of knowledge
The knowledge piece set that mode was stored, and organized, manages and used in computer storage interknit.These knowledge pieces include
Knowwhy relevant with field, factual data, the heuristic knowledge obtained by expertise are determined as related in certain field
Justice, theorem and algorithm and common sense knowledge etc..
Wherein, the dialogue carried out with above-mentioned user can be that single-wheel is talked with, or more wheel dialogues, the present embodiment is to this
It does not select, the present embodiment is illustrated by taking more wheel dialogues as an example.
Binding modules 1203 for above-mentioned first keyword to be combined with above-mentioned second keyword, obtain above-mentioned user's
Treat answer problem;
Matching module 1204, for being matched in above structure question and answer knowledge base using the mode of similarity calculation
State the Similar Problems for treating answer problem;
Module 1205 is retrieved, for the answer of the above-mentioned Similar Problems of retrieval acquisition in above structure question and answer knowledge base;
Specifically, binding modules 1203 obtain above-mentioned user treat answer problem after, matching module 1204 can make
The above-mentioned Similar Problems for treating answer problem are matched in above structure question and answer knowledge base with the mode of similarity calculation, so as to
Achieve the purpose that meet user demand.Such as:User's treats that answer problem can be described as after more wheel dialogues:" inter-bank takes energy throughout the year
Cannot reduce or remit ", matching module 1204 by way of similarity calculation, it can be found that " inter-bank is taken throughout the year to be reduced or remitted " with it is upper
It is synonymous statement to state in structuring question and answer knowledge base " whether inter-bank is taken throughout the year reduces or remits ", then " whether inter-bank is taken throughout the year reduces or remits "
The Similar Problems for treating answer problem of as above-mentioned user, therefore acquisition can be retrieved in above structure question and answer knowledge base
The answer of " whether inter-bank is taken throughout the year reduces or remits ".
Certainly, if there are problems that in above structure question and answer knowledge base treating the problem of answer is identical with above-mentioned user,
Above-mentioned user then can be directly retrieved in above structure question and answer knowledge base treat answer problem, obtains above-mentioned user and waits to answer
The answer of multiple problem.
Module 1206 is provided, the answer of Similar Problems for retrieval module 1205 to be retrieved acquisition is supplied to above-mentioned use
Family.
In the above-mentioned question and answer guide device based on artificial intelligence, receiving module 1201 receives the first keyword input by user
Later, module 1202 is obtained according to above-mentioned first keyword, is engaged in the dialogue, obtained based on structuring question and answer knowledge base and above-mentioned user
The second keyword that above-mentioned user inputs in above-mentioned dialog procedure is obtained, binding modules 1203 are crucial by the first keyword and second
Word combines, and obtain above-mentioned user treats answer problem, and matching module 1204 is using the mode of similarity calculation in above structure
The above-mentioned Similar Problems for treating answer problem are matched in question and answer knowledge base, retrieval module 1205 is in above structure question and answer knowledge base
Middle retrieval obtains the answer of above-mentioned Similar Problems, provides module 1206 and the answer of above-mentioned Similar Problems is supplied to above-mentioned user,
It is excavated so as to realize automatically according to keyword input by user, obtain user treats answer problem, it is only necessary to less people
Work participates in, and improves question and answer efficiency.
Figure 13 is the structure diagram of question and answer guide device another embodiment of the application based on artificial intelligence, this implementation
In example, module 1202 is obtained, specifically for when above-mentioned first keyword is problem, based on structuring question and answer knowledge base to above-mentioned
User provides the above problem corresponding at least one concept;Obtain above-mentioned user selected from above-mentioned at least one concept it is general
It reads, alternatively, obtaining above-mentioned concept input by user.Specifically, when above-mentioned first keyword is problem, obtaining module 1202 can
Actively inquire that user wants to ask according to structuring question and answer knowledge base is which corresponding concept of the problem, as shown in Figure 3.
In Fig. 3, it is assumed that the first keyword input by user is " the single limit transferred accounts is how many ", this belongs to problem, in
It can be based on structuring question and answer knowledge base and provide where the corresponding at least one concept of the above problem " could you tell me finger to above-mentioned user
A kind of business:1. inter-bank, which leads to 2. different degree, pays 3. personal mobile phone banks ... ", it then obtains module 1202 and obtains user from above-mentioned
The concept " personal mobile phone bank " selected at least one concept, certainly, if not including user in above-mentioned at least one concept
Want the concept of inquiry, then above-mentioned user can also input the concept that oneself wants inquiry.
Obtain module 1202, specifically for when above-mentioned first keyword be concept when, based on structuring question and answer knowledge base to
Above-mentioned user provides above-mentioned concept corresponding at least one problem;Obtain what above-mentioned user selected from above-mentioned at least one problem
Problem, alternatively, obtaining above-mentioned problem input by user.
Specifically, when above-mentioned first keyword is concept, structuring question and answer knowledge base master can be based on by obtaining module 1202
What dynamic inquiry user wanted to ask is the which aspect problem of the concept, as shown in Figure 5.In Fig. 5, it is assumed that input by user first is crucial
Word is " inter-bank is led to ", this belongs to concept, and above-mentioned concept pair is provided to above-mentioned user in can be based on structuring question and answer knowledge base
At least one problem answered " could you tell me and want what problem led to about inter-bank asked:1. the single limit transferred accounts is how many 2. annual fees
Whether can reduce or remit ... ", it then obtains module 1202 and obtains user the problem of being selected from above-mentioned at least one problem " annual fee is
It is no to reduce or remit ", certainly, if the problem of not wanting inquiry including user in above-mentioned at least one problem, above-mentioned user also may be used
To input the problem of oneself wants inquiry.
In the present embodiment, binding modules 1203 are closed specifically for being based on above structure question and answer knowledge base and above-mentioned first
Keyword understands the second keyword, with the information included to the first keyword and the second keyword carry out automatic filling and
It replaces, obtain above-mentioned user treats answer problem.
Specifically, based on above structure question and answer knowledge base, question and answer guiding can be not only carried out, while can also carry out
Hereafter understand, you can with the knowledge flexibly in above structure question and answer knowledge base and the first keyword to working as the of front-wheel
Two keywords are understood, realize information filling and replacement automatically, obtain above-mentioned user treats answer problem, such as Fig. 7 and Fig. 8 institutes
Show.
In Fig. 7, user is in last round of dialogue, and for " the single limit transferred accounts is how many ", this belongs to the first keyword of input
Problem, " please to the corresponding at least one concept of the above-mentioned user offer above problem in can be based on structuring question and answer knowledge base
Ask that you refer to any business:1. inter-bank, which leads to 2. different degree, pays 3. personal mobile phone banks ... ", then obtain user from it is above-mentioned at least
The concept " personal mobile phone bank " selected in one concept, providing a user answer later, " personal mobile phone bank transfer limit is
5w members ".Talk with when front-wheel, the second keyword input by user is " inter-bank is led to ", and binding modules 1203 are based on above structure
Change question and answer knowledge base and the first keyword, the second keyword is understood, to be closed to above-mentioned first keyword and above-mentioned second
The information that keyword includes fill and replace automatically, and can obtain user treats that answer problem leads to the single limit transferred accounts for inter-bank
Volume is how many, can then provide a user answer " inter-bank leads to limit of transferring accounts for 2w members ".
In Fig. 8, user is in last round of dialogue, and the first keyword of input is " whether inter-bank is taken throughout the year can reduce or remit ", base
The answer " inter-bank is taken throughout the year to be reduced or remitted " of the above problem is provided in structuring question and answer knowledge base to above-mentioned user.When front-wheel pair
Words, the second keyword input by user are " that year, expense was how many ", and binding modules 1203 are based on above structure question and answer knowledge base
With the first keyword, the second keyword is understood, with the letter included to above-mentioned first keyword and above-mentioned second keyword
Breath carry out automatically fill and replace, can obtain user treat answer problem for inter-bank take throughout the year be it is how many, then can to
Family furnishes an answer " it is 20 yuan that inter-bank is taken throughout the year ".
Further, compared with the question and answer guide device based on artificial intelligence shown in Figure 12, the difference lies in Figure 13
The shown question and answer guide device based on artificial intelligence can also include:Word-dividing mode 1207, statistical module 1208, tight ness rating meter
It calculates module 1209, composite module 1210, processing module 1211, filtering module 1212 and problem and obtains module 1213;
Wherein, word-dividing mode 1207, for will treat that the problems in question and answer knowledge base of structuring and answer are divided by sentence
Word;
Statistical module 1208 counts for passing through the word that co-occurrence statistics method obtains participle, obtains statistics letter
Breath, above-mentioned statistical information include current term and other words close to the number of co-occurrence, current term and other words not close to
The total degree that the number of co-occurrence and each word occur;
Tight ness rating computing module 1209, what the statistical information for being obtained according to statistical module 1208 obtained above-mentioned participle
Tight ness rating between word is calculated;Specifically, tight ness rating computing module 1209 can use tight ness rating method, according to above-mentioned
Tight ness rating between the word that statistical information obtains above-mentioned participle calculates.
Composite module 1210 for tight ness rating to be combined more than predetermined threshold and adjacent word, obtains close
Segment;Wherein, above-mentioned predetermined threshold can be in specific implementation, according to the sets itselfs such as system performance and/or realization demand, sheet
Embodiment is not construed as limiting the size of above-mentioned predetermined threshold.
Processing module 1211 for analyzing the problems in above-mentioned question and answer knowledge base for treating structuring and answer, obtains
The rule that the problems in above-mentioned question and answer knowledge base for treating structuring and answer are contained is obtained, by above-mentioned rule to above-mentioned close piece
Duan Jinhang processing obtains initial candidate concept and initial problem set;
Filtering module 1212 for passing through query segment identification technology, is filtered out and is identified as in above-mentioned initial candidate concept
The concept of query segment obtains final concept set, as shown in Figure 10;
Problem obtains module 1213, for according to the problems in above-mentioned question and answer knowledge base for treating structuring and filtering module
1212 obtained final concept set are handled above-mentioned initial problem set by Relation extraction, and acquisition is above-mentioned to treat structure
The problem of in the problem of question and answer knowledge base of change includes with the concept tight association in above-mentioned final concept set, composition are finally asked
Topic set, to obtain above structure question and answer knowledge base, as shown in figure 11.
The present embodiment can be realized is processed as structuring question and answer knowledge base by question and answer knowledge base, and people is carried out to data to reduce
The cost that work is abstracted.
Figure 14 is the structure diagram of the application computer equipment one embodiment, and above computer equipment can include depositing
Reservoir, processor and it is stored in the computer program that can be run on above-mentioned memory and on above-mentioned processor, above-mentioned processor
When performing above computer program, the question and answer bootstrap technique provided by the embodiments of the present application based on artificial intelligence can be realized.
Figure 14 shows the block diagram suitable for being used for the exemplary computer device 12 for realizing the application embodiment.Figure 14 is shown
The computer equipment 12 shown is only an example, should not bring any limit to the function and use scope of the embodiment of the present application
System.
As shown in figure 14, computer equipment 12 is showed in the form of universal computing device.The component of computer equipment 12 can
To include but not limited to:One or more processor or processing unit 16, system storage 28 connect different system component
The bus 18 of (including system storage 28 and processing unit 16).
Bus 18 represents one or more in a few class bus structures, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using the arbitrary bus structures in a variety of bus structures.It lifts
For example, these architectures include but not limited to industry standard architecture (Industry Standard
Architecture;Hereinafter referred to as:ISA) bus, microchannel architecture (Micro Channel Architecture;Below
Referred to as:MAC) bus, enhanced isa bus, Video Electronics Standards Association (Video Electronics Standards
Association;Hereinafter referred to as:VESA) local bus and peripheral component interconnection (Peripheral Component
Interconnection;Hereinafter referred to as:PCI) bus.
Computer equipment 12 typically comprises a variety of computer system readable media.These media can be it is any can be by
The usable medium that computer equipment 12 accesses, including volatile and non-volatile medium, moveable and immovable medium.
System storage 28 can include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (Random Access Memory;Hereinafter referred to as:RAM) 30 and/or cache memory 32.Computer equipment 12
It may further include other removable/nonremovable, volatile/non-volatile computer system storage mediums.Only conduct
Citing, storage system 34 can be used for reading and writing immovable, non-volatile magnetic media, and (Figure 14 do not show, commonly referred to as " hard disk
Driver ").Although being not shown in Figure 14, can provide for moving non-volatile magnetic disk (such as " floppy disk ") read-write
Disc driver and to removable anonvolatile optical disk (such as:Compact disc read-only memory (Compact Disc Read
Only Memory;Hereinafter referred to as:CD-ROM), digital multi CD-ROM (Digital Video Disc Read Only
Memory;Hereinafter referred to as:DVD-ROM) or other optical mediums) read-write CD drive.In these cases, each driving
Device can be connected by one or more data media interfaces with bus 18.Memory 28 can include at least one program and produce
Product, the program product have one group of (for example, at least one) program module, and it is each that these program modules are configured to perform the application
The function of embodiment.
Program/utility 40 with one group of (at least one) program module 42 can be stored in such as memory 28
In, such program module 42 includes --- but being not limited to --- operating system, one or more application program, other programs
Module and program data may include the realization of network environment in each or certain combination in these examples.Program mould
Block 42 usually performs function and/or method in embodiments described herein.
Computer equipment 12 can also be with one or more external equipments 14 (such as keyboard, sensing equipment, display 24
Deng) communication, the equipment interacted with the computer equipment 12 communication can be also enabled a user to one or more and/or with making
The computer equipment 12 any equipment (such as network interface card, the modulatedemodulate that can communicate with one or more of the other computing device
Adjust device etc.) communication.This communication can be carried out by input/output (I/O) interface 22.Also, computer equipment 12 may be used also
To pass through network adapter 20 and one or more network (such as LAN (Local Area Network;Hereinafter referred to as:
LAN), wide area network (Wide Area Network;Hereinafter referred to as:WAN) and/or public network, for example, internet) communication.Such as figure
Shown in 14, network adapter 20 is communicated by bus 18 with other modules of computer equipment 12.Although it should be understood that in Figure 14
It is not shown, computer equipment 12 can be combined and use other hardware and/or software module, including but not limited to:Microcode, equipment
Driver, redundant processing unit, external disk drive array, RAID system, tape drive and data backup storage system
Deng.
Processing unit 16 is stored in program in system storage 28 by operation, so as to perform various functions application and
Data processing, such as realize the question and answer bootstrap technique provided by the embodiments of the present application based on artificial intelligence.
The embodiment of the present application also provides a kind of non-transitorycomputer readable storage medium, is stored thereon with computer journey
Sequence can realize that the question and answer provided by the embodiments of the present application based on artificial intelligence are drawn when above computer program is executed by processor
Guiding method.
Appointing for one or more computer-readable media may be used in above-mentioned non-transitorycomputer readable storage medium
Meaning combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.Computer can
It reads storage medium and for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device
Or device or arbitrary above combination.The more specific example (non exhaustive list) of computer readable storage medium includes:
Electrical connection, portable computer diskette, hard disk, random access memory (RAM), read-only storage with one or more conducting wires
Device (Read Only Memory;Hereinafter referred to as:ROM), erasable programmable read only memory (Erasable
Programmable Read Only Memory;Hereinafter referred to as:EPROM) or flash memory, optical fiber, portable compact disc are read-only deposits
Reservoir (CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer
Readable storage medium storing program for executing can be any tangible medium for including or storing program, which can be commanded execution system, device
Either device use or in connection.
Computer-readable signal media can include in a base band or as a carrier wave part propagation data-signal,
Wherein carry computer-readable program code.Diversified forms may be used in the data-signal of this propagation, including --- but
It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be
Any computer-readable medium other than computer readable storage medium, which can send, propagate or
Transmission for by instruction execution system, device either device use or program in connection.
The program code included on computer-readable medium can be transmitted with any appropriate medium, including --- but it is unlimited
In --- wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
Can with one or more programming language or combinations come write for perform the application operation computer
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully performs, partly perform on the user computer on the user computer, the software package independent as one performs, portion
Divide and partly perform or perform on a remote computer or server completely on the remote computer on the user computer.
It is related in the situation of remote computer, remote computer can pass through the network of any kind --- including LAN (Local
Area Network;Hereinafter referred to as:) or wide area network (Wide Area Network LAN;Hereinafter referred to as:WAN) it is connected to user
Computer or, it may be connected to outer computer (such as passing through Internet connection using ISP).
In the description of this specification, reference term " one embodiment ", " example ", " is specifically shown " some embodiments "
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment or example of the application.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It is combined in an appropriate manner in one or more embodiments or example.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the different embodiments or examples described in this specification and the feature of different embodiments or examples
It closes and combines.
In addition, term " first ", " second " are only used for description purpose, and it is not intended that instruction or hint relative importance
Or the implicit quantity for indicating indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include at least one this feature.In the description of the present application, " multiple " are meant that at least two, such as two, three
It is a etc., unless otherwise specifically defined.
Any process described otherwise above or method description are construed as in flow chart or herein, represent to include
Module, segment or the portion of the code of the executable instruction of one or more the step of being used to implement custom logic function or process
Point, and the range of the preferred embodiment of the application includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, to perform function, this should be by the application
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The system of row system, device or equipment instruction fetch and execute instruction) it uses or combines these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicate, propagate or pass
Defeated program is for instruction execution system, device or equipment or the dress used with reference to these instruction execution systems, device or equipment
It puts.The more specific example (non-exhaustive list) of computer-readable medium is including following:Electricity with one or more wiring
Connecting portion (electronic device), portable computer diskette box (magnetic device), random access memory (Random Access
Memory;Hereinafter referred to as:RAM), read-only memory (Read Only Memory;Hereinafter referred to as:ROM), erasable editable
Read memory (Erasable Programmable Read Only Memory;Hereinafter referred to as:EPROM) or flash memory,
Fiber device and portable optic disk read-only storage (Compact Disc Read Only Memory;Hereinafter referred to as:CD-
ROM).In addition, computer-readable medium can even is that the paper or other suitable media that can print described program on it, because
For can be then suitable with other into edlin, interpretation or when necessary for example by carrying out optical scanner to paper or other media
Mode is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the application can be realized with hardware, software, firmware or combination thereof.Above-mentioned
In embodiment, software that multiple steps or method can in memory and by suitable instruction execution system be performed with storage
Or firmware is realized.Such as, if realized with hardware in another embodiment, following skill well known in the art can be used
Any one of art or their combination are realized:With for data-signal realize logic function logic gates from
Logic circuit is dissipated, the application-specific integrated circuit with suitable combinational logic gate circuit, programmable gate array (Programmable
Gate Array;Hereinafter referred to as:PGA), field programmable gate array (Field Programmable Gate Array;Below
Referred to as:FPGA) etc..
Those skilled in the art are appreciated that realize all or part of step that above-described embodiment method carries
Suddenly it is that relevant hardware can be instructed to complete by program, the program can be stored in a kind of computer-readable storage medium
In matter, the program when being executed, one or a combination set of the step of including embodiment of the method.
In addition, each functional unit in each embodiment of the application can be integrated in a processing module, it can also
That each unit is individually physically present, can also two or more units be integrated in a module.Above-mentioned integrated mould
The form that hardware had both may be used in block is realized, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized in the form of software function module and is independent product sale or in use, can also be stored in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..Although it has been shown and retouches above
Embodiments herein is stated, it is to be understood that above-described embodiment is exemplary, it is impossible to be interpreted as the limit to the application
System, those of ordinary skill in the art can be changed above-described embodiment, change, replace and become within the scope of application
Type.
Claims (12)
1. a kind of question and answer bootstrap technique based on artificial intelligence, which is characterized in that including:
Receive the first keyword input by user;
It according to first keyword, is engaged in the dialogue based on structuring question and answer knowledge base and the user, obtains the user and exist
The second keyword inputted in the dialog procedure;
First keyword is combined with second keyword, obtain the user treats answer problem;
It is matched in the structuring question and answer knowledge base using the mode of similarity calculation and described treats that the similar of answer problem is asked
Topic, and retrieval obtains the answer of the Similar Problems in the structuring question and answer knowledge base;
The answer of the Similar Problems is supplied to the user.
2. according to the method described in claim 1, it is characterized in that, described according to first keyword, asked based on structuring
It answers knowledge base to engage in the dialogue with the user, obtains the second keyword that the user inputs in the dialog procedure and include:
It is corresponding to user offer described problem based on structuring question and answer knowledge base when first keyword is problem
At least one concept;
The concept that the user selects from least one concept is obtained, alternatively, obtaining the concept input by user.
3. according to the method described in claim 1, it is characterized in that, described according to first keyword, asked based on structuring
It answers knowledge base to engage in the dialogue with the user, obtains the second keyword that the user inputs in the dialog procedure and include:
It is corresponding to the user offer concept based on structuring question and answer knowledge base when first keyword is concept
At least one problem;
The problem of user selects from least one problem is obtained, alternatively, obtaining the problem input by user.
It is 4. according to the method described in claim 1, it is characterized in that, described by first keyword and second keyword
With reference to obtain the user treats that answer problem includes:
Based on the structuring question and answer knowledge base and first keyword, second keyword is understood, with to institute
It states the information that the first keyword and second keyword include fill and replace automatically, obtains the user and wait to reply
Problem.
5. according to the method described in any of claim 1 to 4, which is characterized in that described according to first keyword, base
It engages in the dialogue in structuring question and answer knowledge base and the user, obtains the second pass that the user inputs in the dialog procedure
Before keyword, further include:
The problems in question and answer knowledge base for treating structuring and answer are segmented by sentence;
The word obtained by co-occurrence statistics method to participle counts, and obtains statistical information, and the statistical information includes working as
Preceding word and number, the current term of other words close to co-occurrence do not occur with other words close to the number of co-occurrence and each word
Total degree;
Tight ness rating between the word obtained according to the statistical information to the participle calculates;
Tight ness rating is more than predetermined threshold and adjacent word is combined, obtains close segment;
The problems in described question and answer knowledge base for treating structuring and answer are analyzed, treat that the question and answer of structuring are known described in acquisition
Know the rule that the problems in library and answer are contained, the close segment is handled by the rule, obtain initial wait
Select concept and initial problem set;
By query segment identification technology, the concept that query segment is identified as in the initial candidate concept is filtered out, is obtained most
Whole concept set;
According to the problems in described question and answer knowledge base for treating structuring and the final concept set, by Relation extraction to described
Initial problem set is handled, treated described in acquisition in the problem of question and answer knowledge base of structuring includes with the final concept set
The problem of concept tight association in conjunction, final problem set is formed, to obtain the structuring question and answer knowledge base.
6. a kind of question and answer guide device based on artificial intelligence, which is characterized in that including:
Receiving module, for receiving the first keyword input by user;
Obtain module, for the first keyword received according to the receiving module, based on structuring question and answer knowledge base with it is described
User engages in the dialogue, and obtains the second keyword that the user inputs in the dialog procedure;
Binding modules, for first keyword to be combined with second keyword, obtain the user treats that answer is asked
Topic;
Matching module described is waited to reply for matching in the structuring question and answer knowledge base using the mode of similarity calculation
The Similar Problems of problem;
Module is retrieved, for the answer of the retrieval acquisition Similar Problems in the structuring question and answer knowledge base;
Module is provided, the answer of Similar Problems for the retrieval module retrieval to be obtained is supplied to the user.
7. device according to claim 6, which is characterized in that
The acquisition module, specifically for when first keyword is problem, based on structuring question and answer knowledge base to described
User provides described problem corresponding at least one concept;Obtain the user selected from least one concept it is general
It reads, alternatively, obtaining the concept input by user.
8. device according to claim 6, which is characterized in that
The acquisition module, specifically for when first keyword is concept, based on structuring question and answer knowledge base to described
User provides the concept corresponding at least one problem;Obtain that the user selects from least one problem asks
Topic, alternatively, obtaining the problem input by user.
9. device according to claim 6, which is characterized in that
The binding modules, specifically for being based on the structuring question and answer knowledge base and first keyword, to described second
Keyword is understood, is filled and replaced automatically with the information included to first keyword and second keyword
It changes, obtain the user treats answer problem.
10. according to the device described in claim 6-9 any one, which is characterized in that further include:
Word-dividing mode, for will treat that the problems in question and answer knowledge base of structuring and answer are segmented by sentence;
Statistical module counts for passing through the word that co-occurrence statistics method obtains participle, obtains statistical information, the system
It counts information and includes current term and other words close to the number, current term and other words of co-occurrence not close to the number of co-occurrence
The total degree occurred with each word;
Tight ness rating computing module, for according to the statistical information that the statistical module obtains to it is described participle obtain word between
Tight ness rating calculated;
Composite module for tight ness rating to be combined more than predetermined threshold and adjacent word, obtains close segment;
Processing module for analyzing the problems in described question and answer knowledge base for treating structuring and answer, is treated described in acquisition
The rule that the problems in question and answer knowledge base of structuring and answer are contained, by the rule to the close segment at
Reason obtains initial candidate concept and initial problem set;
Filtering module for passing through query segment identification technology, filters out in the initial candidate concept and is identified as query segment
Concept, obtain final concept set;
Problem obtains module, for treating the problems in question and answer knowledge base of structuring according to and the filtering module obtains
Final concept set, handles the initial problem set by Relation extraction, treats that the question and answer of structuring are known described in acquisition
The problem of knowing in the problem of library includes with the concept tight association in the final concept set, forms final problem set, with
Obtain the structuring question and answer knowledge base.
11. a kind of computer equipment, which is characterized in that including memory, processor and be stored on the memory and can be
The computer program run on the processor when the processor performs the computer program, realizes such as claim 1-5
In any method.
12. a kind of non-transitorycomputer readable storage medium, is stored thereon with computer program, which is characterized in that the meter
The method as described in any in claim 1-5 is realized when calculation machine program is executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711447824.3A CN108170792B (en) | 2017-12-27 | 2017-12-27 | Question and answer guiding method and device based on artificial intelligence and computer equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711447824.3A CN108170792B (en) | 2017-12-27 | 2017-12-27 | Question and answer guiding method and device based on artificial intelligence and computer equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108170792A true CN108170792A (en) | 2018-06-15 |
CN108170792B CN108170792B (en) | 2021-12-28 |
Family
ID=62518407
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711447824.3A Active CN108170792B (en) | 2017-12-27 | 2017-12-27 | Question and answer guiding method and device based on artificial intelligence and computer equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108170792B (en) |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109065172A (en) * | 2018-07-04 | 2018-12-21 | 平安科技(深圳)有限公司 | Illness information acquisition method, device, computer equipment and storage medium |
CN109241519A (en) * | 2018-06-28 | 2019-01-18 | 平安科技(深圳)有限公司 | Environmental Evaluation Model acquisition methods and device, computer equipment and storage medium |
CN109614467A (en) * | 2018-11-23 | 2019-04-12 | 北京仿真中心 | A kind of knowledge connection based on segment-similarity and dynamic organization's method and system |
CN109885219A (en) * | 2018-12-29 | 2019-06-14 | 航天信息股份有限公司 | Business handling bootstrap technique, device and computer readable storage medium |
CN110222161A (en) * | 2019-05-07 | 2019-09-10 | 北京来也网络科技有限公司 | Talk with robot intelligent response method and device |
CN110309378A (en) * | 2019-06-28 | 2019-10-08 | 深圳前海微众银行股份有限公司 | A kind of processing method that problem replies, apparatus and system |
CN110414246A (en) * | 2019-06-19 | 2019-11-05 | 平安科技(深圳)有限公司 | Shared file method for managing security, device, terminal and storage medium |
CN110443382A (en) * | 2019-07-09 | 2019-11-12 | 青岛聚好联科技有限公司 | A kind of user interaction approach based on intelligent customer service platform |
CN110795542A (en) * | 2019-08-28 | 2020-02-14 | 腾讯科技(深圳)有限公司 | Dialogue method and related device and equipment |
CN110970021A (en) * | 2018-09-30 | 2020-04-07 | 航天信息股份有限公司 | Question-answering control method, device and system |
CN111159364A (en) * | 2018-11-07 | 2020-05-15 | 株式会社东芝 | Dialogue system, dialogue device, dialogue method, and storage medium |
CN111242431A (en) * | 2019-12-31 | 2020-06-05 | 联想(北京)有限公司 | Information processing method and device, and method and device for constructing customer service conversation workflow |
CN111324712A (en) * | 2020-02-18 | 2020-06-23 | 山东汇贸电子口岸有限公司 | Dialogue reply method and server |
CN111353017A (en) * | 2020-02-20 | 2020-06-30 | 上海智臻智能网络科技股份有限公司 | Intelligent interaction method and device |
CN111414467A (en) * | 2020-03-20 | 2020-07-14 | 中国建设银行股份有限公司 | Question-answer dialogue method and device, electronic equipment and computer readable storage medium |
CN111914073A (en) * | 2020-07-15 | 2020-11-10 | 中国联合网络通信集团有限公司 | Customer service response method, device, equipment and storage medium |
CN112399019A (en) * | 2020-09-16 | 2021-02-23 | 中国农业银行股份有限公司河北省分行 | Intelligent outbound call method, terminal equipment and readable storage medium |
CN112911073A (en) * | 2019-04-30 | 2021-06-04 | 五竹科技(北京)有限公司 | Intelligent knowledge graph construction method and device for outbound process conversation content |
CN113282734A (en) * | 2021-06-28 | 2021-08-20 | 中国平安人寿保险股份有限公司 | Question-answer processing method, device, equipment and medium based on structured data |
CN113342925A (en) * | 2020-02-18 | 2021-09-03 | 株式会社东芝 | Interface providing device, interface providing method, and program |
CN113590790A (en) * | 2021-07-30 | 2021-11-02 | 北京壹心壹翼科技有限公司 | Question retrieval method, device, equipment and medium applied to multiple rounds of question answering |
CN115344679A (en) * | 2022-08-16 | 2022-11-15 | 中国平安财产保险股份有限公司 | Problem data processing method and device, computer equipment and storage medium |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104573028A (en) * | 2015-01-14 | 2015-04-29 | 百度在线网络技术(北京)有限公司 | Intelligent question-answer implementing method and system |
CN104820681A (en) * | 2015-04-17 | 2015-08-05 | 清华大学 | Response method and system for online Q&A service |
CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术(北京)有限公司 | Man-machine interaction method and system based on artificial intelligence |
CN105183850A (en) * | 2015-09-07 | 2015-12-23 | 百度在线网络技术(北京)有限公司 | Information querying method and device based on artificial intelligence |
CN105528437A (en) * | 2015-12-17 | 2016-04-27 | 浙江大学 | Question-answering system construction method based on structured text knowledge extraction |
CN106294340A (en) * | 2015-05-12 | 2017-01-04 | 中兴通讯股份有限公司 | A kind of intelligent customer service processing method and device thereof |
CN106610952A (en) * | 2016-09-30 | 2017-05-03 | 四川用联信息技术有限公司 | Mixed text feature word extraction method |
CN106649844A (en) * | 2016-12-30 | 2017-05-10 | 浙江工商大学 | Unstructured text data enhanced distributed large-scale data dimension extracting method |
US20170140277A1 (en) * | 2015-11-17 | 2017-05-18 | International Business Machines Corporation | Computer-implemented cognitive system for assessing subjective question-answers |
US20170220541A1 (en) * | 2016-02-02 | 2017-08-03 | International Business Machines Corporation | Recommending form field augmentation based upon unstructured data |
US20170270120A1 (en) * | 2016-03-15 | 2017-09-21 | International Business Machines Corporation | Question transformation in question answer systems |
CN107220380A (en) * | 2017-06-27 | 2017-09-29 | 北京百度网讯科技有限公司 | Question and answer based on artificial intelligence recommend method, device and computer equipment |
CN107305550A (en) * | 2016-04-19 | 2017-10-31 | 中兴通讯股份有限公司 | A kind of intelligent answer method and device |
-
2017
- 2017-12-27 CN CN201711447824.3A patent/CN108170792B/en active Active
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104573028A (en) * | 2015-01-14 | 2015-04-29 | 百度在线网络技术(北京)有限公司 | Intelligent question-answer implementing method and system |
CN104820681A (en) * | 2015-04-17 | 2015-08-05 | 清华大学 | Response method and system for online Q&A service |
CN106294340A (en) * | 2015-05-12 | 2017-01-04 | 中兴通讯股份有限公司 | A kind of intelligent customer service processing method and device thereof |
CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术(北京)有限公司 | Man-machine interaction method and system based on artificial intelligence |
CN105183850A (en) * | 2015-09-07 | 2015-12-23 | 百度在线网络技术(北京)有限公司 | Information querying method and device based on artificial intelligence |
US20170140277A1 (en) * | 2015-11-17 | 2017-05-18 | International Business Machines Corporation | Computer-implemented cognitive system for assessing subjective question-answers |
CN105528437A (en) * | 2015-12-17 | 2016-04-27 | 浙江大学 | Question-answering system construction method based on structured text knowledge extraction |
US20170220541A1 (en) * | 2016-02-02 | 2017-08-03 | International Business Machines Corporation | Recommending form field augmentation based upon unstructured data |
US20170270120A1 (en) * | 2016-03-15 | 2017-09-21 | International Business Machines Corporation | Question transformation in question answer systems |
CN107305550A (en) * | 2016-04-19 | 2017-10-31 | 中兴通讯股份有限公司 | A kind of intelligent answer method and device |
CN106610952A (en) * | 2016-09-30 | 2017-05-03 | 四川用联信息技术有限公司 | Mixed text feature word extraction method |
CN106649844A (en) * | 2016-12-30 | 2017-05-10 | 浙江工商大学 | Unstructured text data enhanced distributed large-scale data dimension extracting method |
CN107220380A (en) * | 2017-06-27 | 2017-09-29 | 北京百度网讯科技有限公司 | Question and answer based on artificial intelligence recommend method, device and computer equipment |
Cited By (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109241519A (en) * | 2018-06-28 | 2019-01-18 | 平安科技(深圳)有限公司 | Environmental Evaluation Model acquisition methods and device, computer equipment and storage medium |
CN109065172B (en) * | 2018-07-04 | 2023-04-11 | 平安科技(深圳)有限公司 | Disease information acquisition method and device, computer equipment and storage medium |
CN109065172A (en) * | 2018-07-04 | 2018-12-21 | 平安科技(深圳)有限公司 | Illness information acquisition method, device, computer equipment and storage medium |
CN110970021B (en) * | 2018-09-30 | 2022-03-08 | 航天信息股份有限公司 | Question-answering control method, device and system |
CN110970021A (en) * | 2018-09-30 | 2020-04-07 | 航天信息股份有限公司 | Question-answering control method, device and system |
CN111159364B (en) * | 2018-11-07 | 2023-10-03 | 株式会社东芝 | Dialogue system, dialogue device, dialogue method, and storage medium |
CN111159364A (en) * | 2018-11-07 | 2020-05-15 | 株式会社东芝 | Dialogue system, dialogue device, dialogue method, and storage medium |
CN109614467A (en) * | 2018-11-23 | 2019-04-12 | 北京仿真中心 | A kind of knowledge connection based on segment-similarity and dynamic organization's method and system |
CN109885219A (en) * | 2018-12-29 | 2019-06-14 | 航天信息股份有限公司 | Business handling bootstrap technique, device and computer readable storage medium |
CN112911073A (en) * | 2019-04-30 | 2021-06-04 | 五竹科技(北京)有限公司 | Intelligent knowledge graph construction method and device for outbound process conversation content |
CN110222161A (en) * | 2019-05-07 | 2019-09-10 | 北京来也网络科技有限公司 | Talk with robot intelligent response method and device |
CN110414246A (en) * | 2019-06-19 | 2019-11-05 | 平安科技(深圳)有限公司 | Shared file method for managing security, device, terminal and storage medium |
CN110414246B (en) * | 2019-06-19 | 2023-05-30 | 平安科技(深圳)有限公司 | Shared file security management method, device, terminal and storage medium |
CN110309378A (en) * | 2019-06-28 | 2019-10-08 | 深圳前海微众银行股份有限公司 | A kind of processing method that problem replies, apparatus and system |
CN110443382A (en) * | 2019-07-09 | 2019-11-12 | 青岛聚好联科技有限公司 | A kind of user interaction approach based on intelligent customer service platform |
CN110795542B (en) * | 2019-08-28 | 2024-03-15 | 腾讯科技(深圳)有限公司 | Dialogue method, related device and equipment |
CN110795542A (en) * | 2019-08-28 | 2020-02-14 | 腾讯科技(深圳)有限公司 | Dialogue method and related device and equipment |
CN111242431A (en) * | 2019-12-31 | 2020-06-05 | 联想(北京)有限公司 | Information processing method and device, and method and device for constructing customer service conversation workflow |
CN111324712A (en) * | 2020-02-18 | 2020-06-23 | 山东汇贸电子口岸有限公司 | Dialogue reply method and server |
CN113342925A (en) * | 2020-02-18 | 2021-09-03 | 株式会社东芝 | Interface providing device, interface providing method, and program |
CN111353017A (en) * | 2020-02-20 | 2020-06-30 | 上海智臻智能网络科技股份有限公司 | Intelligent interaction method and device |
CN111414467A (en) * | 2020-03-20 | 2020-07-14 | 中国建设银行股份有限公司 | Question-answer dialogue method and device, electronic equipment and computer readable storage medium |
CN111914073A (en) * | 2020-07-15 | 2020-11-10 | 中国联合网络通信集团有限公司 | Customer service response method, device, equipment and storage medium |
CN112399019A (en) * | 2020-09-16 | 2021-02-23 | 中国农业银行股份有限公司河北省分行 | Intelligent outbound call method, terminal equipment and readable storage medium |
CN113282734A (en) * | 2021-06-28 | 2021-08-20 | 中国平安人寿保险股份有限公司 | Question-answer processing method, device, equipment and medium based on structured data |
CN113590790A (en) * | 2021-07-30 | 2021-11-02 | 北京壹心壹翼科技有限公司 | Question retrieval method, device, equipment and medium applied to multiple rounds of question answering |
CN113590790B (en) * | 2021-07-30 | 2023-11-28 | 北京壹心壹翼科技有限公司 | Question retrieval method, device, equipment and medium applied to multi-round question and answer |
CN115344679A (en) * | 2022-08-16 | 2022-11-15 | 中国平安财产保险股份有限公司 | Problem data processing method and device, computer equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN108170792B (en) | 2021-12-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108170792A (en) | Question and answer bootstrap technique, device and computer equipment based on artificial intelligence | |
CN110377740B (en) | Emotion polarity analysis method and device, electronic equipment and storage medium | |
CN106095834A (en) | Intelligent dialogue method and system based on topic | |
CN108170773A (en) | Media event method for digging, device, computer equipment and storage medium | |
CN104573099B (en) | The searching method and device of topic | |
CN109271493A (en) | A kind of language text processing method, device and storage medium | |
CN107220355A (en) | News Quality estimation method, equipment and storage medium based on artificial intelligence | |
CN103678269A (en) | Information processing method and device | |
CN107423894A (en) | The task measures and procedures for the examination and approval, device and computer equipment | |
CN108090211A (en) | Hot news method for pushing and device | |
CN113590776A (en) | Text processing method and device based on knowledge graph, electronic equipment and medium | |
CN108897869A (en) | Corpus labeling method, device, equipment and storage medium | |
CN108415939A (en) | Dialog process method, apparatus, equipment and computer readable storage medium based on artificial intelligence | |
CN109815500A (en) | Management method, device, computer equipment and the storage medium of unstructured official document | |
CN114840662A (en) | Event information extraction method and device and electronic equipment | |
CN108153904A (en) | Language material collection method, device and computer equipment | |
CN115374771A (en) | Text label determination method and device | |
CN110020163A (en) | Searching method, device, computer equipment and storage medium based on human-computer interaction | |
CN107704549A (en) | Voice search method, device and computer equipment | |
CN116402166B (en) | Training method and device of prediction model, electronic equipment and storage medium | |
CN109800410A (en) | A kind of list generation method and system based on online chatting record | |
CN114969195B (en) | Dialogue content mining method and dialogue content evaluation model generation method | |
CN111159370A (en) | Short-session new problem generation method, storage medium and man-machine interaction device | |
CN110377891A (en) | Generation method, device, equipment and the computer readable storage medium of event analysis article | |
CN103678355B (en) | Text mining method and text mining device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |